Inference
EN

Gemini 3.7 Flash vs MiMo-V2.6-Pro

Change models
Gemini 3.7 FlashGoogle
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
68.5 ±2.2
70.2 ±4.7 best
GapIndex points below the top.
−1.7 · no clear gap
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
85/s best
31/s
EloLMArena rating and rank.
1489
1492 best
ReleasedMonth of release.
2026-08
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.75
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$3.75
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.38
$1.31 best
1K documents20K tokens in, 1K out, each.
$18.75
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$225.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.1
72.1 best
CodingCode writing and repair.
66.9 best
66.6
ReasoningLogic problems and puzzles.
68.7 best
68.3
MultimodalTasks with images and text.
67.7
—
KnowledgeFacts and expert knowledge.
71.2 best
64.2
MultilingualTasks in many languages.
72.3
—
InstructionTasks with strict prompt rules.
88.3
—
MathMath problems.
66.8
71.3 best

Benchmarks

37 shared
Only Gemini 3.7 Flash: 56Only MiMo-V2.6-Pro: 21
Gemini 3.7 Flash
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
47.9%18 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
81.7%33 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
14.3%52 / 214
26.6% best19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
55.3% best12 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
44.6%40 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
70.4%48 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
57.2%21 / 114
60.9% best8 / 114
MedScribeHealthcare
83.9%40 / 109
88.3% best13 / 109
MedCodeHealthcare
53.4% best9 / 106
45.0%39 / 106
Legal Research BenchLegal
34.6%49 / 90
47.1% best16 / 90
Terminal-Bench 2.1 · BenchLMAgentic
85.8%17 / 86
89.9% best4 / 86
Tax Agent BenchFinance
22.8%48 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
68.0%59 / 80
72.3% best49 / 80
LiveBench ReasoningReasoning
87.8% best26 / 80
79.6%59 / 80
Finance Agent (v2)Finance
59.0% best7 / 79
57.3%16 / 79
Code MigrationCoding
34.8%37 / 77
43.0% best26 / 77
EMBFinance
71.3% best13 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
77.5% best14 / 75
67.8%32 / 75
ProgramBenchCoding
0.0%34 / 65
0.5% best19 / 65
Terminal-Bench 4.0Agentic
12.1%42 / 61
31.3% best24 / 61